agentmods.dev

ai-instructions: Skill for Claude Code

.github/skills/clean-slate-workspace/SKILL.md

clean-slate-workspace is a skill for Claude Code from lsampaioweb/ai-instructions. It costs 22 tokens per session (376 once invoked), scanned A, original, MIT.

A controlled cleanup process for artifacts created during the current chat. It identifies ownership before removing anything and preserves user-authored or uncertain files.

In plain words
What is it for?
Use it when you want to inspect and remove chat-created files, plans, temporary artifacts, or session materials and verify what remains.
Why use it?
It helps restore a workspace without accidentally deleting existing project work. Deletion requires explicit confirmation and is limited to artifacts created in the chat.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

This is lsampaioweb/ai-instructions's own configuration. It tells Claude Code how to work on ai-instructions itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-instructions configures →

not rated 1repo changed 12d ago A scan 22 tokens original MIT
View source ↗ lsampaioweb/ai-instructions
Reuse

Borrowing it

Nothing to install: this file belongs to lsampaioweb/ai-instructions. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lsampaioweb/ai-instructions/main/.github/skills/clean-slate-workspace/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lsampaioweb/ai-instructions

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for clean-slate-workspace

README.md
[![agentmods](https://agentmods.dev/badge/skills/lsampaioweb/ai-instructions/clean-slate-workspace/github.svg)](https://agentmods.dev/skills/lsampaioweb/ai-instructions/clean-slate-workspace)
Your own site
<a href="https://agentmods.dev/skills/lsampaioweb/ai-instructions/clean-slate-workspace"><img src="https://agentmods.dev/badge/skills/lsampaioweb/ai-instructions/clean-slate-workspace/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for clean-slate-workspace

Your own site · 80×15
<a href="https://agentmods.dev/skills/lsampaioweb/ai-instructions/clean-slate-workspace"><img src="https://agentmods.dev/badge/skills/lsampaioweb/ai-instructions/clean-slate-workspace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 376 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.00376
Opus 5.5 $0.00009 $0.00150
Sonnet 5.5 $0.00004 $0.00075
Haiku 4.5 $0.00002 $0.00038

Measured 12d ago against content hash 62c5ac61d1c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

clean-slate-workspace scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.github/skills/clean-slate-workspace/SKILL.md · 47 lines

What it actually says

Clean Slate Workspace

1. Inspect the Workspace

  1. Inspect current conversation artifacts in the active workspace.
  2. List all files, plans, repository memory, session memory, and temporary artifacts created in this chat.
  3. Determine ownership for each artifact.

2. Resolution Rules

  • Do not delete anything until inspection is complete and targets are listed.
  • Delete only artifacts created in this chat.
  • Treat ambiguous ownership as user-authored.
  • Never delete or modify user-authored files or ambiguous-ownership artifacts.
  • Do not touch persistent user-level memories or reusable customizations unless they were created for this workspace in this chat.
  • Remove empty directories left by deletions.
  • Confirm no session-created files or empty directories remain after deletion.
  • If no session-created artifacts exist, state that explicitly and stop.

3. Safety Guards

  • Execution boundary: Delete only after presenting the target list and receiving the user's explicit confirmation.

4. Review Plan Layout

Use this exact markdown schema:

Scope

  • Target:
  • Mode: <read-only | apply-after-confirmation>

Result

  • Summary:

Evidence

  • Deleted: <none | item1; item2>
  • Preserved: <none | item1; item2>
  • Uncertainties: <none | item1; item2>

Next Action

  • <single minimal next step or none>

Verdict

  • READY | NEEDS FIXES | BLOCKED
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago Changed · +9 lines · -32 tokens per session 62c5ac61d1c0
  2. 2mo ago First seen · 38 lines · 54 tokens per session scan A 77aa3cbe0459

Subscribe to this mod's changes

clean-slate-workspace is a skill published in the GitHub repository lsampaioweb/ai-instructions (1 stars, last pushed 5d ago), licensed MIT. It adds 22 tokens to every session and 376 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

clean-slate-workspace compared with skills from other repositories

clean-slate-workspace next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
clean-slate-workspacelsampaioweb/ai-instructionsSkill15d agoMITA22Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143ktodayMITA103Claude Code